AI Engineer

Pragma Edge Software Services; Hyderabad; On-site; INR 2,500,000 - 4,200,000; Full time

Job summary

Pragma Edge Software Services in Hyderabad is seeking a Senior AI Engineer to own end-to-end AI solutions, including agentic AI, multi-agent architectures, and NLP systems. You will design and deploy agent-based workflows, integrate LLMs with tools and data stores, and collaborate with product and data teams to scale production AI capabilities.

Proficiency in Python, PyTorch/TensorFlow, and RAG is essential.

Qualifications

• Bachelors or Masters in Computer Science, AI, Data Science or related fields.
• 3–5 years hands-on AI/ML or NLP experience.
• Strong Python proficiency.
• Experience with LLMs, prompt engineering, fine-tuning, and RAG.

Responsibilities

• Design and implement agent-based and multi-agent systems.
• Develop LLM applications and optimize prompts and control loops.
• Deploy AI services and agent workflows to production.
• Optimize latency, cost, memory usage, and scalability.
• Collaborate with product, research, data engineering, and software teams.
• Mentor junior engineers and contribute to design reviews.

Skills

Agentic AI

Multi-agent orchestration

NLP & LLMs

Python

Prompt engineering

Distributed systems

Problem solving

Communication

Education

Bachelor's or Master's in Computer Science/AI/Data Science

Tools

PyTorch

TensorFlow

LangChain

LangGraph

AutoGen

CrewAI

Job description

Job Overview:

We are looking for a Senior AI Engineer with proven experience in Agentic AI, Large Language Models (LLMs), and advanced NLP systems. The candidate will take end-to-end ownership of multi-agent architectures, from design and development through production deployment and optimization.

Key Responsibilities:

1. Agentic AI & Multi-Agent Architecture

• Design and implement agent-based and multi-agent systems using frameworks such as CrewAI, LangGraph, AutoGen, and LangChain
• Build autonomous agents capable of planning, reasoning, tool usage, and long-running task execution
• Integrate LLMs with tools, APIs, memory stores, vector databases, and RAG pipelines

2. LLM Development & Optimization

• Fine-tune and optimize foundation models (e.g., Mistral, Gemini Flash, OpenAI models, AWS Bedrock)
• Develop advanced prompt strategies and control loops for agent reasoning
• Build NLP pipelines for summarization, classification, QA, and text generation

3. Production Deployment & Scalability

• Deploy AI services and agent workflows to production environments
• Optimize solutions for latency, cost, memory usage, and scalability
• Collaborate with DevOps and platform teams on CI/CD, monitoring, and reliability

4. Evaluation, Safety & Reliability

• Implement evaluation frameworks for LLM and agent performance
• Ensure robustness, observability, and responsible AI deployment
• Apply AI safety, ethical AI, and governance best practices

5. Cross-Functional Collaboration

• Work closely with product, research, data engineering, and software teams
• Translate business requirements into scalable AI solutions
• Mentor junior engineers and contribute to design reviews

6. Documentation & Knowledge Sharing

• Maintain detailed technical documentation
• Communicate system design, trade-offs, and outcomes to stakeholders

Required Qualifications:

• Bachelors or Masters degree in Computer Science, AI, Data Science, or related fields
• 3-5 years of hands‑on experience in AI/ML or applied NLP
• Strong proficiency in Python
• Experience with PyTorch and/or TensorFlow
• Hands‑on experience with LLMs, prompt engineering, fine‑tuning, and RAG
• Practical exposure to agentic AI and multi-agent orchestration
• Experience building scalable, distributed systems
• Strong problem‑solving and communication skills

Preferred / Nice-to-Have Skills:

• Experience with WatsonX, LangChain, AutoGen, LangGraph, CrewAI
• Cloud platforms: IBM Cloud, AWS, Azure, or GCP
• Experience with vector databases (FAISS, Pinecone, Weaviate, etc.)
• Contributions to open-source AI projects
• Knowledge of AI safety, alignment, and ethical AI principles